blue archive flux — FLUX AI Model

Recommended resolution: Short side 1152+, long side 1920+. Landscape focuses on the scene, portrait focuses on the character.. Hirs repair can be opened at 1.5 to 2 (optional), no trigger words. The base model used for training isFlux.1-Dev, How This Model Is Trained - This model is trained with , the images are generated with - The is maintained by , fork by me. - The step we auto-selected is 200 ep to balance the fidelity and controllability of the model. Why Not Just Using The Better-Selected Images Our model's entire process, from data crawling, training, to generating preview images and publishing, is 100% automated without any human intervention. It's an interesting experiment conducted by our team, and for this purpose, we have developed a complete set of software infrastructure, including data filtering, automatic training, and automated publishing. Therefore, if possible, we would appreciate more feedback or suggestions as they are highly valuable to us. Why We Can't Accurately Generate the Desired Art Style Our current training data is sourced from a variety of image websites. Predicting the specific art styles present in official images within a fully automated pipeline presents a significant challenge. As a result, the generation of art styles relies on clustering based on labels from the training dataset, striving for the best possible reproduction. We will continue to tackle this issue and seek optimization, but it remains a challenge that cannot be entirely resolved. The accuracy of art style reproduction is also unlikely to match the level achieved by manually trained models. For the following groups, it is not recommended to use this model and we express regret: - Individuals who cannot tolerate any deviations from the original art style, even in the slightest detail. - Individuals who are facing application scenarios with high demands for accuracy in art style reproduction. - Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm. - Individuals who are not comfortable with the fully automated process of training art style models using LoRA, or those who believe that art style training must be done purely through manual operations to maintain the integrity of the original artistic vision. - Individuals who finds the generated image content offensive to their values. Why Do We Use Auto-Training Framework I just need to put the images there, and the rest of the steps are fully automatic, requiring no supervision. I can go play games or hang out, completely without the need for any tedious data processing and labeling work, and the speed of data processing and training is very fast. This method of model training is a complete enjoyment for me.

1,730 downloads · 172 likes on Civitai

SHA256

BD436506578AD66323175219AE6E82BB7E16BAB34A73909DD04F999DA315FA46

ModelTrends.ai Model ID

#15775

Flag content

Example renders

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.

Get this prompt

Render by KLK420 on Civitai

Flag

Settings

Sampler

Undefined

Steps

Guidance

3.5

Seed

1318883020

Size

832x1216

Clip skip

Weight used

0.45

Prompt

Create a highly detailed close-up image of a fantasy elf’s face, blending elements of cinematic art and modern digital design. Her pale skin glows with a soft, ethereal light, intricately adorned with golden, cracked patterns that evoke the delicate art of kintsugi, tracing along her features with a mystical glow. These patterns intertwine with neon tattoos, forming geometric shapes that pulse with a magical energy. Her large, mesmerizing eyes shift between shades of deep teal and oceanic blue, as if holding the mysteries of the sea within them, drawing the viewer into her intense, calm gaze. Her long, silver hair cascades around her face, adding a touch of otherworldly elegance, while subtle, futuristic design elements—like squares and geometric motifs inspired by Kazimir Malevich—blend seamlessly with the organic patterns. The background is a dark, starry sky with a minimalist aesthetic, enhancing the dreamy and enigmatic atmosphere. The composition features sharp focus and a shallow depth of field, capturing every detail in a moody, cinematic style, with film grain, bokeh effects, and a vignette that adds a professional, high-budget feel. The image fuses modern and analog styles, creating a stunning portrait that is both epic and ethereal, embodying the beauty of contemporary digital art and the timeless allure of classic fantasy. b74_aes, DreamArt, detail eyes, magic eyes, de01,

Render by SomeAIGuy on Civitai

Flag

Settings

Sampler

Undefined

Steps

Guidance

3.5

Seed

3036169137

Size

832x1216

Clip skip

Weight used

Prompt

An adult woman standing in the forest. She's wearing a sports jacket over a tanktop, as well as racing shorts and a black cap. She has short blonde hair and green eyes. She's grinning. She is waving with one hand and has her other hand on her hip Blue Archive Style

Render by Yuno779 on Civitai

Flag

Settings

Sampler

Euler

Steps

Guidance

Seed

3959964909

Size

1152x1920

Prompt

1girl, very long hair, ponytail, medium breasts, blush, blue eyes, blue shirt, solo, blue footwear, sweat, open clothes, parted lips, star \(sky\), open shorts, gloves, gym shirt, shorts, halo, blue shorts, nipples, bare shoulders, sleeveless, short sleeves, official alternate costume, partially fingerless gloves, looking at viewer, indoors, gym storeroom, mechanical halo, sleeveless shirt, shirt, short shorts, vaulting horse, track jacket, breasts, midriff, blue jacket, shoes, shirt lift, sky, white shirt, starry sky, clothes lift, open jacket, white socks, loafers, black shirt, star sticker, blue sky, sticker on face, jacket, sitting, jacket around waist, socks, long hair, spread legs, black footwear <lora:BastylrV2:1>

Render by SkullKnight_01 on Civitai

Flag

Settings

Sampler

Euler

Steps

Guidance

Seed

3119089700

Size

836x1216

Prompt

surrealist art sci-fi style masterpiece, highres, Image of a space marine on the shores of Hell pointing at the viewer holding a scroll that says "No se MASTURBEN!", (upper body:1.2), solo focus, green armor, gray helmet, <lora:BastylrV2:1> . futuristic, technological, alien worlds, space themes, advanced civilizations . dreamlike, mysterious, provocative, symbolic, intricate, detailed

Negative prompt

ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, historical, medieval, anime, photorealistic, realistic, deformed, glitch, noisy, low contrast

Render by Yuno779 on Civitai

Flag

Settings

Sampler

Euler

Steps

Guidance

Seed

27758636

Size

1920x1152

Prompt

1girl, hair bell, full moon, solo, wide sleeves, yellow eyes, east asian architecture, looking at viewer, muneate, architecture, hair ornament, hakama skirt, long hair, jingle bell, red hair, armor, bow \(weapon\), petals, breastplate, red sky, serious, moon, tattoo, cherry blossoms, shoulder armor, torii, hakama, pauldrons, sword, katana, weapon, wolf, japanese clothes, animal ears, skirt, hip vent, wind, bell, bridge, fox ears, sky <lora:BastylrV2:1>

Render by Lzpera on Civitai

Flag

Settings

Sampler

DPM++ 2M

Steps

Guidance

Seed

3345161446

Size

540x960

Prompt

1girl,solo,azusa (blue archive),hair ornament,flower,wings,hair flower,long hair,halo,purple eyes,white hair,holding flower,looking at viewer,school uniform,bangs,hair between eyes,white jacket,feathered wings,dress,white wings,long sleeves,sailor collar,jacket,black dress,from side,black sailor collar,Blurred background,artist:rella,artist:torino,artist:gomzi,multicolored eyes,depth of field,simple background,floating ribbon,hpflower,<lora:add-detail-xl:1>,<lora:backlighting_il_2_d16:1>,(backlighting:0.5),<lora:NOOB_vp1_detailer_by_volnovik_v1:1>,<lora:WSSKX_WAI:0.8>,<lora:blue_archive-ixl-style-soralz:1>,<lora:BastylrV2:1>,, masterpiece,amazing quality,best quality,absurd,newest,High Resolution,More Details,8K,UHD,

Negative prompt

(negative_v2 Color_Balance_Calibration_0.8),lazyhand lazyneg,lazynsfw,lazypos,, negative_v2 Color_Balance_Calibration_0.8,easynegative,lowres,bad quality,low quality,old,3d,

Render by Yuno779 on Civitai

Flag

Settings

Sampler

Euler

Steps

Guidance

Seed

792663921

Size

1920x1152

Prompt

1girl, skirt, medium breasts, hair scrunchie, yellow flower, very long hair, hair ornament, looking at viewer, purple eyes, day, blue bow, white shirt, closed mouth, dutch angle, hair flower, long sleeves, school uniform, hand up, scrunchie, twintails, blue sailor collar, low twintails, depth of field, sailor collar, solo, shirt, pleated skirt, blurry background, blush, vase, smile, serafuku, flower, red flower, breasts, blue skirt, building, blurry, white scrunchie, sidelocks, bow, light brown hair, sunflower, long hair <lora:BastylrV2:1>

Render by Yuno779 on Civitai

Flag

Settings

Sampler

Euler

Steps

Guidance

Seed

2239340289

Size

1920x1152

Prompt

1girl, frills, hair bow, flower, frilled sleeves, smile, sunlight, hat ribbon, nature, forest, brown footwear, tree, holding, letterboxed, closed eyes, blonde hair, solo focus, white headwear, holding flower, long hair, ribbon, outdoors, sunflower, hat, :3, sitting, leaf, frilled shirt collar, red ribbon, plant, long sleeves, :d, open mouth, witch hat, blush, boots, red bow, wide sleeves, grass, day, bow, =_= <lora:BastylrV2:1>

Similar Models

AI Models for Image, Video & Text Generation

blue archive flux is a LoRA for the Flux family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Flux models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

More Flux models More Flux LoRAs anime gaming artstyles style

Browse by Model Family